Tizona — verification and routing for autonomous agents MCP Server

by tizonaintelligence Your server? Claim it

answering

Tizona — verification and routing for autonomous agents is answering right now. Last checked 14 min ago. It exposes 17 tools.

Verification and routing for autonomous agents: crawler ID, email, web capture, data routing.

Uptime history 10 days of history

10 days agonow

100.0%

Uptime 24h

91 of 91 checks

Tools

read from the server

185 ms

Response time

average over 24h

open, no key

Access

streamable-http

Tools have disappeared from this server

A tool that vanishes takes a piece of your agent with it, and the change arrives silently. Watch this server and every such change lands in your inbox.

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 14 min ago.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add tizona --transport http https://tizonaintelligence.com/mcp

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "tizona": {
      "url": "https://tizonaintelligence.com/mcp"
    }
  }
}

~/.codex/config.toml

[mcp_servers.tizona]
url = "https://tizonaintelligence.com/mcp"

.cursor/mcp.json

{
  "mcpServers": {
    "tizona": {
      "url": "https://tizonaintelligence.com/mcp"
    }
  }
}

.vscode/mcp.json

{
  "mcpServers": {
    "tizona": {
      "url": "https://tizonaintelligence.com/mcp"
    }
  }
}

Available tools 17

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

award

award_allowances

Allowances for an Australian modern award, from the Fair Work Commission MAPD. "kind"=wage (leading hand, first aid, tool) or expense (meal, travel, vehicle). By award code (e.g. "MA000009") or fixed id. Returns each allowance's amount, all-purpose flag and payment frequency, verbatim (CC BY 4.0). Dollar values only: does NOT determine which allowance applies — read with the award, which prevails. Not legal advice.

award_pay_rate

Minimum pay rates for an Australian modern award, from the Fair Work Commission MAPD. Input an award code (e.g. "MA000009") or fixed id, optionally filtered by classification level or employee-rate-type. Returns each classification's base and calculated rate with operative dates, verbatim from the FWC and stamped with version/published-year (CC BY 4.0). Dollar values only: does NOT say which award or classification applies, or what is payable — read with the award, which prevails. Not legal advice; unknown award throws.

award_penalties

Penalty rates (weekend, public holiday, overtime, shift) for an Australian modern award, from the Fair Work Commission MAPD. By award code (e.g. "MA000009") or fixed id, optionally by classification level or employee-rate-type. Returns each penalty's multiplier/percentage and the FWC's own calculated dollar value, verbatim (CC BY 4.0). Dollar values only: does NOT determine which penalty applies to a shift — read with the award, which prevails. Not legal advice; unknown award throws.

verify

verify_ai_crawler

FREE. Is a crawler who it claims to be, by the strongest available method. CRYPTOGRAPHIC (best): pass a Web Bot Auth signature (RFC 9421) with its signatureInput, signatureAgent and url — we fetch the operator's published key and verify it (proof of key control, not just network origin). NETWORK: pass a source ip with userAgent/claimed — we check the operator's published IP ranges (OpenAI, Anthropic, Google, Perplexity, Bing, Apple, DuckDuckGo, Common Crawl, Mistral, Kagi, and more). Returns verified, spoofed, unrecognised, or indeterminate; never calls a claim spoofed when it merely cannot be checked.

verify_email_address

FREE. Validate an email before spending a send, token, or signup — no mail sent, no SMTP probe. Checks RFC-5322 syntax, live MX over DNS (and names the provider), disposable domains, role mailboxes (info@ — custom domains only, never freemail), and typos (gmial.com to gmail.com). Returns one verdict (deliverable, undeliverable, disposable, role_address, typo_suspected, or invalid), a 0-100 deliverability score, the canonical mailbox for dedup, and a verdict hash. Confirms domain reachability, not that a specific mailbox exists.

calculate

calculate_gst

Add GST to a GST-exclusive amount, or extract the GST from a GST-inclusive amount, in exact integer cents. GST in an inclusive price is one ELEVENTH, not one tenth. "basis" is required — "exclusive" adds, "inclusive" extracts (synonyms accepted); an unknown basis throws rather than returning a wrong figure.

compare

compare_entity_names

Score whether two names are the same entity, 0 to 1, with the reasoning broken out. Knows 81 spellings of 30 legal forms across 21 countries ("Pty. Ltd." = "Proprietary Limited"), ignores word order ("Smith, John" = "John Smith"), and down-weights generic words (so "Woolworths Group" and "Coles Group" stay distinct). Flags obfuscation (homoglyphs, invisible characters, digit substitution) in an "obfuscation" field. Check "distinctiveness": names of only generic words identify weakly however well they match.

crawler

check_ai_crawler_access

FREE. Before fetching a URL, learn whether your crawler identity will be served, refused, or met by a paid tollgate (Cloudflare Pay Per Crawl, TollBit, a bare 402) — from a standing census, with the price where published and whether the site varies by user-agent. Unknown URLs return "unknown" and schedule themselves. Bulk: triage_ai_crawler_access. Observational (a datacenter vantage), not a guarantee.

deduplicate

deduplicate_entity_names

Cluster up to 250 names into groups that are the same entity — the work behind a CRM merge or supplier-list cleanup. Grouped by distinctive words, not compared exhaustively; the response reports how many comparisons ran. If one word dominates the list, "truncated" is true (clustering incomplete) — split and retry.

match

match_entity_name

Score one name against up to 750 candidates; returns those over the threshold, ranked, each tagged with its index in the input array. compare_entity_names applied as a search (legal-form-, word-order- and obfuscation-aware). Over 750 candidates throws rather than truncating.

normalise

normalise_entity_name

Reduce a name to its comparable core with the legal form split out — a stable, deterministic grouping key. Reports every token removed and flags any obfuscation it strips (homoglyphs, invisible characters, digit-for-letter substitution). The normalisation the matching tools apply, exposed on its own.

pull

pull_ai_crawler_watch

Given a watchId from watch_ai_crawler_access, returns the URLs whose access changed since your last pull (started refusing, a tollgate appeared, a price moved) and nothing for those unchanged. The first pull reports the starting state. Each pull spends one credit whether or not anything changed.

superannuation

superannuation_guarantee

Compute the Australian Superannuation Guarantee on a qualifying-earnings amount, exact to the cent. Returns the SG, the rate, the earnings subject to SG after the annual maximum-contributions-base cap, and the financial year used. Computed the CURRENT way — from 1 July 2026 the base is qualifying earnings (not OTE) and the cap is annual, under Payday Super, so old quarterly-OTE code is now wrong. You supply the qualifying-earnings figure; this does NOT define what counts as qualifying earnings. ATO-sourced, not tax advice. Current financial year only; an out-of-range date throws.

total

total_invoice

Total a multi-line invoice in integer cents, handling GST-free lines and both ATO rounding methods (per-line and total-based), and report the exact discrepancy between them — an invoice must not mix them. A malformed line throws.

triage

triage_ai_crawler_access

Check up to 200 URLs in one call for AI-crawler access — which your identity can read, which refuse it, and which sit behind a paid tollgate — with a summary to branch on before spending a fetch. Unknown URLs cost nothing and schedule themselves; known URLs are metered. Observational (what a datacenter vantage saw), not a guarantee; a user-agent is a claim, not a credential.

validate

validate_australian_identifier

Validate an Australian ABN, ACN, ARBN, TFN, Medicare or BSB against its official checksum. Offline and deterministic; whitespace and hyphens ignored; a valid ABN also flags whether the holder is a company. A pass proves the digits are internally consistent (catches typos and fabrications); it does NOT prove the identifier is issued, active, or held by anyone. BSB has no check digit: format only. Unknown scheme throws.

watch

watch_ai_crawler_access

Register a set of URLs and pre-buy pull credits; the census watches them for access changes — a paywall appearing, an identity refused, a tollgate. Returns a watchId (bearer token — keep it secret). Pull changes with pull_ai_crawler_watch. Adds are free, pulls are paid; a watch expires after inactivity.

Tools removed

These were exposed before and are gone now. No other catalogue tracks this.

sanctions_dataset_version

removed 29 Aug 2026

screen_against_sanctions

removed 29 Aug 2026

capture_web_page_with_proof

removed 30 Aug 2026

verify_web_page_attestation

removed 30 Aug 2026

pull_award_watch

removed 31 Aug 2026

watch_award_rates

removed 31 Aug 2026

Endpoints

URL	Transport	State	Latency	Checked
https://tizonaintelligence.com/mcp	streamable-http	answering	367 ms	14 min ago

Alternatives to Tizona — verification and routing for autonomous agents

same job, measured the same way

Mailsink

by heocoi

Disposable inboxes for AI agents and CI: catch the verification email, read the OTP or link.

74 installs/wk local only

Agenticmail

by agenticmail

Real email and SMS for AI agents — send mail, receive verification codes, drive a real inbox.

240 installs/wk local only

Temp Mail

by temp-mail

Disposable email inboxes for AI agents — read messages and verification codes.

answering

agentsbase — Email for AI Agents

by agentsbase

Email for AI agents. Create mailboxes, send/receive emails, and auto-extract verification codes.

33 installs/wk local only

Machine Inbox

by machineinbox

Task-scoped email inboxes for AI agents: read mail, extract verification codes, and reply.

11 tools answering

DevInbox

by devinbox

Real email inboxes for AI agents: create inboxes, catch verification codes, extract OTPs, reply.

answering

smails

by pexni

Free disposable email for AI agents: a throwaway inbox to read verification codes over MCP.

73 installs/wk local only

Bounceprotect

by fahassan00

Email validation and SMTP verification for Claude Desktop, Cursor, and Claude Code.

121 installs/wk local only

Tizona — verification and routing for autonomous agents — questions

Answers built from our own checks of this server.

What can Tizona — verification and routing for autonomous agents do?

It exposes 17 tools, read directly from the server on our last check. Among them: award_allowances, award_pay_rate, award_penalties, calculate_gst, check_ai_crawler_access, compare_entity_names and 11 more. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →

What is Tizona — verification and routing for autonomous agents mostly used for?

Its tools cluster around award and verify. That is what this server is built to work with — the grouping comes from the actual tool names, not from a category we assigned.

Is Tizona — verification and routing for autonomous agents working right now?

We send a real MCP handshake every 15 minutes. Over the last 24 hours 91 of 91 checks got a reply (100.0%), average response time 185 ms. The bar chart above shows every period we have measured.

Did Tizona — verification and routing for autonomous agents ever remove tools?

Yes. sanctions_dataset_version, screen_against_sanctions, capture_web_page_with_proof, verify_web_page_attestation and 2 more are no longer exposed — we recorded the date each one disappeared. A tool vanishing usually means a breaking change for anything that depended on it.

How do I connect Tizona — verification and routing for autonomous agents?

Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.

Does Tizona — verification and routing for autonomous agents need an API key?

No. Tizona — verification and routing for autonomous agents completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 17 of them are readable on this page. This is what we observed, not what the docs claim.

How fast is Tizona — verification and routing for autonomous agents?

It answers our handshake in 185 ms on average, which is faster than 75% of all working MCP servers we measure. That puts it in the quick quarter of the ecosystem. The comparison comes from our own checks across the whole registry, every 15 minutes.